Analyzing chronic disease biomarkers using electrochemical sensors and artificial neural networks

Chronic diseases are persistent health conditions that affect our quality of life, increase morbidity and mortality, and are a global challenge. Further, the increasing prevalence of chronic diseases requires the development of new methods for the early detection of these disease-specific biomarkers. Here, we provide a concise review of the chronic disease biomarkers acquired by electrochemical sensors. Then, we discuss the potential of artificial neural networks on the sensed data for disease monitoring and management. Next, we describe risk factors, causes, pathophysiological processes, and severity of chronic diseases. This is followed with a careful review of how we can use the sensed chronic disease biomarkers and clinical symptoms as features for the machine learning algorithms. Finally, we discuss how uncovered patterns in the biosensors' data using artificial neural networks can be used to predict and diagnose chronic diseases. We believe this review will help in developing artificial neural network-based innovative analytical tools for chronic diseases and other healthcare applications in future. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

This article provides a concise review of chronic disease biomarkers acquired by electrochemical sensors and discusses the potential of artificial neural networks in disease monitoring and management. It also describes risk factors, causes, pathophysiological processes, and severity of chronic diseases, as well as how sensed biomarkers and clinical symptoms can be used as features for machine learning algorithms. Finally, it explores how patterns in biosensor data uncovered by artificial neural networks can be used to predict and diagnose chronic diseases. This review will contribute to the development of artificial neural network-based analytical tools for chronic diseases and other healthcare applications in the future.